horizon94

guardrails

Adding guardrails to large language models.

jsonformer

A Bulletproof Way to Generate Structured JSON from Language Models

Viscacha

Viscacha：通用信息抽取数据集收集

llama.cpp

LLM inference in C/C++

Promptify

Prompt Engineering | Prompt Versioning | Use GPT or other prompt based models to get structured output. Join our discord for Prompt-Engineering, LLMs and other latest research

kor

LLM(😽)

guidance

A guidance language for controlling large language models.

lm-format-enforcer

Enforce the output format (JSON Schema, Regex etc) of a language model

CogVideo

Text-to-video generation: CogVideoX (2024) and CogVideo (ICLR 2023)

outlines

Structured Text Generation

lmdeploy

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

tensorrtllm_backend

The Triton TensorRT-LLM Backend

TensorRT-LLM

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

ChatTTS

A generative speech model for daily dialogue.

KVQuant

KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization

nanoLM

An Affordable LLM Pre-training Benchmark via Accurate Loss Prediction across Scales

rationalizing-neural-predictions

[in progress] pytorch implementation of Tao Lei's rationalizing neural predictions

alpaca_eval

An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.

FairEval

optimum-nvidia

LLMTest_NeedleInAHaystack2

Doing simple retrieval from LLM models at various context lengths to measure accuracy

LLMTest_NeedleInAHaystack

Doing simple retrieval from LLM models at various context lengths to measure accuracy

InternLM

Official release of InternLM2.5 base and chat models. 1M context support

Long-Context-Data-Engineering

Implementation of paper Data Engineering for Scaling Language Models to 128K Context

magvit2-pytorch

Implementation of MagViT2 Tokenizer in Pytorch

magvit

Official JAX implementation of MAGVIT: Masked Generative Video Transformer

SEED

Official implementation of SEED-LLaMA (ICLR 2024).

deduplicate-text-datasets

AI-Gaokao

Gaokao Benchmark for AI